Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions or discussions about specific topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific topic throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icons
    -0.89
    izont
    -0.75
    icone
    -0.74
    mates
    -0.74
    othing
    -0.72
    acers
    -0.69
    owed
    -0.69
    gress
    -0.69
    educ
    -0.65
    vl
    -0.65
    POSITIVE LOGITS
     topic
    1.51
     issue
    1.12
     matter
    1.12
     phenomenon
    1.11
     subject
    1.09
     pesky
    1.05
     aspect
    1.00
     elusive
    0.96
     particular
    0.95
     Topic
    0.92
    Act Density 0.141%

    No Known Activations